| { |
| "best_global_step": 10, |
| "best_metric": 2.016936779022217, |
| "best_model_checkpoint": "/tmp/checkpoints_/job_2accba6a-f0a9-48c0-8e37-e9d5970f7a77/checkpoint-10", |
| "epoch": 1.0, |
| "eval_steps": 50, |
| "global_step": 10, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.1, |
| "grad_norm": 1.8589162826538086, |
| "learning_rate": 0.0, |
| "loss": 2.4498867988586426, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 1.9830790758132935, |
| "learning_rate": 6e-06, |
| "loss": 2.458357810974121, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 1.7803077697753906, |
| "learning_rate": 1.2e-05, |
| "loss": 2.521699905395508, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 2.0905215740203857, |
| "learning_rate": 1.8e-05, |
| "loss": 2.6683785915374756, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 1.203072428703308, |
| "learning_rate": 2.4e-05, |
| "loss": 2.0486295223236084, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 1.428836703300476, |
| "learning_rate": 3e-05, |
| "loss": 2.064033031463623, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 1.8449537754058838, |
| "learning_rate": 2.4e-05, |
| "loss": 2.4706876277923584, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.8648535013198853, |
| "learning_rate": 1.8e-05, |
| "loss": 2.5328779220581055, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 2.344430685043335, |
| "learning_rate": 1.2e-05, |
| "loss": 2.575979471206665, |
| "step": 9 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.1865334510803223, |
| "learning_rate": 6e-06, |
| "loss": 1.6627534627914429, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.016936779022217, |
| "eval_runtime": 0.6505, |
| "eval_samples_per_second": 7.686, |
| "eval_steps_per_second": 3.074, |
| "step": 10 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 10, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 39221572009728.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
